The purpose of the present invention is to reduce required calculation resources for image smoothing based on weighted least squares. The image processing device 100 includes: a first smoothing unit 110 for applying one-dimensional first smoothing processing based on weighted least squares to an input image in a first direction per a predetermined number of lines; and a second smoothing unit 120 for applying one-dimensional second smoothing processing based on weighted least squares to the first-smoothing-processed input image in a second direction, which is different from the first direction, per a predetermined block.
Legal claims defining the scope of protection, as filed with the USPTO.
1. An image processing device comprising: a memory; and a processor coupled to the memory and configured to: execute one-dimensional first smoothing processing based on a weighted least squares method on an input image in each predetermined line in a first direction; and execute one-dimensional second smoothing processing based on a weighted least squares method on the input image on which the first smoothing processing has been performed, for each predetermined block in a second direction different from the first direction.
2. The image processing device according to claim 1 , wherein the processor is configured to execute the second smoothing processing for each block depending on redundancy; cumulatively add input images on which the second smoothing processing has been executed; and normalize the cumulatively added input image according to the redundancy.
3. The image processing device according to claim 2 , wherein the redundancy varies depending on an image feature value in the second direction of a guide image related to the input image.
4. The image processing device according to claim 3 , wherein the image feature value represents a difference in a pixel value between a pixel in the guide image and one or more pixels adjacent to the pixel.
5. The image processing device according to claim 2 , wherein the redundancy matching a size of the block is used.
6. An image processing method comprising: executing one-dimensional first smoothing processing based on a weighted least squares method on an input image in each predetermined line in a first direction; and executing one-dimensional second smoothing processing based on a weighted least squares method on the input image on which the first smoothing processing has been performed, for each predetermined block in a second direction different from the first direction.
7. The image processing method according to claim 6 , further comprising executing the second smoothing processing for each block according to redundancy; cumulatively adding input images on which the second smoothing processing has been executed; and normalizing the cumulatively added input image according to the redundancy.
8. The image processing method according to claim 7 , wherein the redundancy varies depending on an image feature amount in the second direction of a guide image related to the input image.
9. The image processing method according to claim 8 , wherein the image feature amount represents a difference in a pixel value between a pixel in the guide image and one or more pixels adjacent to the pixel.
10. The image processing method according to claim 7 , wherein the redundancy matching a size of the block is used.
11. A non-transitory computer-readable storage medium storing a program that causes a computer to perform: processing for executing one-dimensional first smoothing processing based on a weighted least squares method on an input image in each predetermined line in a first direction; and processing for executing one-dimensional second smoothing processing based on a weighted least squares method on the input image on which the first smoothing processing has been performed, for each predetermined block in a second direction different from the first direction.
12. The storage medium according to claim 11 , wherein the program further causes the computer to perform: executing the second smoothing processing for each block according to redundancy; cumulatively adding input images on which the second smoothing processing has been executed; and normalizing the cumulatively added input image according to the redundancy.
13. The storage medium according to claim 12 , wherein the redundancy varies depending on an image feature amount in the second direction of a guide image related to the input image.
14. The storage medium according to claim 13 , wherein the image feature amount represents a difference in a pixel value between a pixel in the guide image and one or more pixels adjacent to the pixel.
15. The storage medium according to claim 12 , wherein the redundancy matching a size of the block is used.
Cooperative Patent Classification codes for this invention. Click any code to explore related patents in that topic.
June 13, 2017
November 24, 2020
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.